Fig. 4

Scenario 2 partitioning schemes. Light gray colored boxes show parts of the data which we used as the training set (T) for parameter estimation. Dark gray colored boxes show parts which we used as validation sets (V). Different background colors represent different partitioning schemes and are consistent with the colors used in the graphs in the Results and discussion section. Each partitioning scheme offered the use of three subsets of the Hog1PP data as the training set. These are the lowest dose subset of each cell type in the lowest dose scheme and the highest of each in the highest dose scheme. The remaining fifteen subsets of the Hog1PP data could be used for validation, separately. These are the lowest dose subset of each cell type in (a) the lowest dose scheme and the highest of each in (b) the highest dose scheme